Abstract-Banks are essential to the global financial system, and one of their primary sources of income comes from loan interest. However, if borrowers fail to repay these loans, it can turn profits into substantial losses, highlighting the importance of assessing the risk of default before approving a loan. Machine learning techniques can be an effective method for quickly and accurately evaluating whether a credit risk should be approved. This study explored six machine learning models—Decision Tree, Random Forest, Support Vector Machine (SVM), Multi-layer Perceptron (MLP) Artificial Neural Network, Naive Bayes, and a stacking ensemble model—to predict the credit risk associated with a loan. Using a dataset of twenty factors typically found in loan applications, the stacking ensemble model achieved the highest accuracy at 78.75%. The Random Forest model, though slightly less accurate at 78.15%, was more efficient while yielding comparable results. Key factors such as credit amount, account status, age, loan duration, and loan purpose were identified as the most influential indicators of credit risk. The findings of this research further support the efficacy of machine learning models for predicting loan default risk.

Abstract-The spread of fake news has become a significant concern in today’s society, as misleading information can easily damage reputations and lives. To address this issue, researchers have developed fake news detection systems using machine learning techniques. The identification of fake news is rapidly gaining traction and is increasingly being adopted by various industries, either for their own use or to offer as a service to others. Machine learning (ML) and deep learning (DL) are two prominent approaches employed to determine the authenticity of news. There are various methods available for detecting false news through both ML and DL techniques. This paper presents a comprehensive analysis of fake news detection using machine learning approaches. Upon thorough examination, it was found that several ML and DL algorithms have been applied in this domain, with the Support Vector Machine (SVM) being the most commonly used ML method, and Long Short-Term Memory (LSTM) being the most widely applied DL technique.

Abstract-This paper proposes the coordinated control of a hybrid AC/DC power system with renewable energy source, energy storages and critical loads. The hybrid microgrid consists of both AC and DC sides. A synchronous generator and a PV farm supply power to the system’s AC and DC sides, respectively. A bidirectional fully controlled AC/DC converter with active and reactive power decoupling technique is used to link the AC bus with the DC bus while regulating the system voltage and frequency. A DC/DC boost converter with a maximum power point tracking (MPPT) function is implemented to maximize the energy generation from the PV farm. Current controlled bidirectional DC/DC converters are applied to connect each lithium-ion battery bank to the DC bus. Lithium-ion battery banks act as energy storage devices that serve to increase the system stability by absorbing or injecting power to the grid as ancillary services. The proposed system can function in both grid-connected mode and islanding mode.

Abstract-Innovative technology is becoming more necessary when it comes to sustainability and solving global environmental issues. “Tech for the Planet: Digital Innovations in Sustainability” analyzes how the development of digital technologies is changing sustainability efforts in different industries and ecosystems. The study investigates the uses of artificial intelligence (AI), the Internet of Things (IoT), blockchain, and data analytics in achieving resource optimization, environmental footprint minimization, and climate change adaptation enhancement. These technologies support smart planning and sustainable practices by enabling precise monitoring and transparent decision-making, as well as real-time data accessibility for stakeholders. The abstract focuses on real case studies and demonstrates how different digital innovations transform the energy, agricultural, transportation, and waste management industries. It also looks at important issues like digital divide, privacy issues of data, and the carbon emission of digital frameworks. The study advocates for a multi-stakeholder effort and emphasizes the role of governments, businesses, and communities in addressing technology’s impact on planetary health. This document calls attention to how digital innovations can facilitate a desirable transition toward a sustainable world while promoting necessary policies and actions.

Abstract-Entrepreneurs play an important role in the development of a nation. Entrepreneurship helps improve the per capita income of a country by generating new job opportunities. It plays a significant role in increasing Gross National Product. As the GNP grows, the per capita income (PCI) also rises, leading to enhanced economic well-being for the population. Entrepreneurs in the rural parts of India are vital for checking the rate of migration of people to bigger towns and cities as they create opportunities for the rural communities. This study focus on the various factors influencing the growth and development of entrepreneurship by studying the self-help groups within Kolasib district of Mizoram state, India. The study analyse primary and secondary data collected from the respondents through structured questionnaire and personal interview. It adopts statistical tools like correlations, reliability test and factor analysis to find out the factors responsible for bringing this positive changes. The study found that these factors can be classified into three categories –internal support, eternal support and personal traits. The study also suggests the government to disclose various central and state schemes for the greater development of entrepreneurship within the state.

Abstract-This paper presents a novel voice- controlled e-commerce platform tailored for visually impaired users. The proposed system integrates advanced artificial intelligence (AI) techniques, including state-of-the-art speech recognition, natural language processing (NLP), and machine learning algorithms, to enhance accuracy, personalization, and overall user experience. Unique workflow diagrams illustrate the operational flow of the system as well as the specific AI modules that power contextual understanding and command execution. Experimental evaluations indicate that the integration of AI leads to significant improvements in accessibility navigation, making digital commerce more inclusive.

Abstract-Law enforcement agents can anticipate smart glasses as the next wearable technology evolution which provides innovative and enhanced crime detection capabilities. The paper develops an Intelligent Criminal Detection System (ICDS) which uses smart glasses together with artificial intelligence (AI) and machine learning (ML) features for system deployment. The system development provides police forces with better capabilities to record evidence in real time through improved facial recognition functionality. Fast suspect recognition becomes achievable through the ICDS because of Viola-Jones algorithm integration with OpenCV and YOLOv8 technology which maintains excellent performance in dynamic busy surveillance areas. This paper investigates smart glass engineering dynamics together with their contemporary implementation by police departments to understand their substantial impact on current law enforcement methods. The research evaluates devastating consequences of smart system deployment which includes privacy breaches and data security vulnerabilities together with subjects being misidentified incorrectly. The system architecture identifies the process in which smart glasses interface with police databases and current data systems. The system performance evaluation takes place in simulated environments through tests that verify its operational efficiency against conventional practices by assessing speed accuracy and dependability. This paper investigates smart glass deployment activities from real police departments at Dubai Police and New York Police Department to establish their usage in investigative functions. Research development will follow two main paths according to the paper including the improvement of real-time feedback algorithms alongside affordable systems and ethical frameworks to gain public trust. This paper includes recommended legislation which promotes appropriate use of smart glasses during law enforcement operations alongside the specified protocols. The study combines modern technology with practical field experience to expand criminal detection system knowledge about smart glass deployment.

Abstract-Customer Relationship Management (CRM) systems play a crucial role in enhancing customer satisfaction, retention, and overall business growth. This paper presents a comprehensive design and implementation framework for a CRM system tailored for the automobile industry. The proposed system integrates lead management, booking management, service history tracking, feedback processing, customer retention strategies, and real-time reporting. The objective is to provide a centralized platform that improves customer engagement, streamlines operations, and delivers actionable insights to the business. The system’s architecture, data flow, user interface design, and performance evaluation are discussed in detail. This research highlights the benefits of automation and predictive analysis in customer relationship management for the automobile sector.

Abstract-The rapid growth of digital technologies has led to an exponential rise in cyber threats, making traditional security measures inadequate in combating sophisticated cyberattacks. Artificial Intelligence (AI) has emerged as a crucial technology in cybersecurity, offering enhanced threat detection through machine learning, deep learning, and behavioral analytics. AI-driven cybersecurity solutions can analyze vast datasets in real time, detect anomalies, predict potential attacks, and automate threat mitigation. By leveraging AI, organizations can strengthen their defense mechanisms against evolving cyber threats, including ransomware, phishing, and advanced persistent threats (APTs). This paper delves into the role of AI in cybersecurity, focusing on its applications in real-time threat detection, anomaly identification, and predictive analytics. Additionally, it examines the advantages, challenges, and future trends in AI-driven cybersecurity, emphasizing the importance of integrating AI with other security technologies to create a robust defense ecosystem. The findings suggest that AI-powered cybersecurity solutions significantly enhance security resilience, but ethical concerns, adversarial AI attacks, and implementation challenges must be addressed for widespread adoption.

Abstract-Automatic text summarization and zero-shot classification are crucial tasks in natural language processing (NLP), aiding in information retrieval, content compression, and text classification. Recent advances in deep learning and transformers have significantly improved the accuracy and efficiency of these tasks. This study evaluates multiple state-of-the-art transformer-based models for text summarization, including Google’s T5, PEGASUS, Facebook’s BART, and Longformer Encoder-Decoder (LED). We assess their performance using the ROUGE and BERTScore metrics to determine their effectiveness in generating concise and contextually accurate summaries. The T5 model, pre-trained on C4, achieves state-of-the-art results on many NLP benchmarks while being flexible enough to be fine-tuned to a variety of important downstream tasks [1]. Also, zero-shot classification with the facebook/bart-large-mnli model is considered in this work, with no training labels beforehand for classification of text into predefined categories. Classification accuracy for a variety of domains, including Politics, Sport, Technology, Entertainment, and Business, is considered in analysis. To classify even more precisely, a corpus with labels is fine-tuned with the BART model and improvement in prediction accuracy and loss over a range of training runs measured. Zero-shot classification, useful for general categories, is seen to have improvement room in specific domains for classification. Classification with fine-tuning of the BART model reduces evaluation loss but comes with hyperparameter search and a larger corpus for even heightened accuracy. Traditionally, zero-shot learning (ZSL) most often referred to a fairly specific type of task: learn a classifier on one set of labels and then evaluate on a different set of labels that the classifier has never seen before [2].